CN111368971A - Unmanned aerial vehicle cluster cooperative landing sequencing method and system - Google Patents
Unmanned aerial vehicle cluster cooperative landing sequencing method and system Download PDFInfo
- Publication number
- CN111368971A CN111368971A CN202010101115.5A CN202010101115A CN111368971A CN 111368971 A CN111368971 A CN 111368971A CN 202010101115 A CN202010101115 A CN 202010101115A CN 111368971 A CN111368971 A CN 111368971A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- failure probability
- cluster
- landing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012163 sequencing technique Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 28
- 239000013598 vector Substances 0.000 claims description 56
- 230000036541 health Effects 0.000 claims description 45
- 230000015556 catabolic process Effects 0.000 claims description 44
- 238000006731 degradation reaction Methods 0.000 claims description 44
- 230000007423 decrease Effects 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000001537 neural effect Effects 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 11
- 238000013139 quantization Methods 0.000 claims description 9
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 7
- 238000005315 distribution function Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000000704 physical effect Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000009826 distribution Methods 0.000 description 7
- 210000002569 neuron Anatomy 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000593 degrading effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A cooperative landing sequencing method for an unmanned aerial vehicle cluster comprises the following steps: each unmanned aerial vehicle in the unmanned aerial vehicle cluster calculates the failure probability predicted value of the unmanned aerial vehicle according to the respective operation state data; each unmanned aerial vehicle communicates with other unmanned aerial vehicles in the unmanned aerial vehicle cluster to obtain failure probability predicted values of all unmanned aerial vehicles; and determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability predicted value. According to the technical scheme, the reliability prediction method is adopted, the unmanned aerial vehicle clusters are sorted through the difference of physical properties, and the subjectivity of manually specifying or randomly selecting the landing sequence of the unmanned aerial vehicle by a program is avoided.
Description
Technical Field
The invention relates to the application field of a group intelligent operating system, in particular to a method and a system for sequencing cooperative landing of unmanned aerial vehicle clusters.
Background
The unmanned aerial vehicle cluster is a formation formed by unmanned aerial vehicle cluster entities which are close in space, have the same intention, are complementary in function and are mutually cooperated. The unmanned aerial vehicle cluster has the advantages of high efficiency, strong expandability, mutual cooperation and parallel work among the unmanned aerial vehicles in the cluster, and wide application in multiple fields of military reconnaissance, regional patrol, material handling, terrain detection and the like. In unmanned aerial vehicle accident statistics, 60% -70% of accidents occur in the process of takeoff and landing.
The manager of the unmanned aerial vehicle cluster can be a pilot or a ground station. The manager can uniformly manage the followers to execute the cooperative landing tasks. However, once a manager breaks down, the communication topology will gradually spread to the communication network of the whole unmanned aerial vehicle cluster, and finally the unmanned aerial vehicles cannot cooperatively land, and even the risk of collision and crash occurs. One way to solve the problem is to make each unmanned aerial vehicle have the function of independently executing the landing procedure, and each unmanned aerial vehicle knows the landing sequence number of itself, and the unmanned aerial vehicle in the cluster executes the landing process according to the sequence number by the way of setting the clock difference or the message broadcast by the procedure. If artificial appointed or procedure random selection unmanned aerial vehicle's descending sequence number, can not guarantee the preferential descending of the relatively poor unmanned aerial vehicle of reliability this moment, can increase the probability that the descending process takes place the risk of falling.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides an unmanned aerial vehicle cluster cooperative landing sequencing method and system.
The technical scheme provided by the invention is as follows:
in a method of sequencing coordinated landing of a cluster of unmanned aerial vehicles, the improvement comprising:
each unmanned aerial vehicle in the unmanned aerial vehicle cluster calculates the failure probability predicted value of the unmanned aerial vehicle according to the respective operation state data;
each unmanned aerial vehicle communicates with other unmanned aerial vehicles in the unmanned aerial vehicle cluster to obtain failure probability predicted values of all unmanned aerial vehicles;
and determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability predicted value.
Preferably, the calculating, by each drone in the drone cluster, a failure probability prediction value of each drone according to respective operating state data includes:
each unmanned aerial vehicle calculates the health characteristic value thereof according to the respective running state data;
and calculating the failure probability predicted value of the health characteristic value according to the health characteristic value.
Preferably, communicating each drone with other drones in the cluster of drones includes communicating with each drone via a communication link
Each unmanned aerial vehicle broadcasts a failure probability predicted value in the unmanned aerial vehicle cluster; and simultaneously subscribing the failure probability predicted values of other unmanned aerial vehicles.
Preferably, determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability prediction value comprises:
and each unmanned aerial vehicle selects the unmanned aerial vehicle with the minimum failure probability predicted value from the acquired failure probability predicted values of all unmanned aerial vehicles including the unmanned aerial vehicle to land finally.
Preferably, the health characteristic value is an euclidean distance between current operating state data of the unmanned aerial vehicle and positive sample data, or an euclidean distance between an input vector and a best matching neural unit;
the input vector is a vector formed by a one-dimensional vector formed by rough features corresponding to the current operation state data of the unmanned aerial vehicle in a certain time period.
Preferably, the euclidean distance between the current operating state data and the positive sample data is calculated according to the following formula:
in the formula (d)ij: the Euclidean distance between the state data of the unmanned aerial vehicle with the number i in the jth operation period and the positive sample data; m: the number of the coarse characteristic values collected in the jth operation period; xik: the current state data is the state data of the unmanned aerial vehicle with the number i in the jth operation cycle; u. ofik: positive sample data; i: numbering unmanned aerial vehicles;j: the jth run cycle.
Preferably, the euclidean distance between the input vector u (t) and the best matching neural unit is calculated as follows:
in the formula: MQEt: the euclidean distance between the input vector u (t) and the BMU, i.e., the minimum quantization error; u (t): inputting a vector; BMU: a best matching neural unit of the self-organizing feature mapping model; f: a matrix Frobenius norm; t: the t-th time period;
preferably, the calculating the failure probability prediction value of the health characteristic value according to the health characteristic value comprises:
taking the health characteristic value as a decline characteristic value, and constructing a performance decline track model of the unmanned aerial vehicle by adopting a classical decline model;
sampling and calculating the performance degradation track model parameters by adopting a Monte Carlo method to obtain a possible degradation track;
and calculating a failure probability predicted value in a future operation period according to the possible decline orbit and a preset soft threshold value.
Preferably, the performance degradation trajectory model is as follows:
yij＝η(τij,0,βi)+ξij
in the formula, yijHealth characteristic value of unmanned plane with number i in operation period j, η function describing performance degradation variable, phi constant, βiThe decline rate of the unmanned plane with number i ξij: error terms of uncertainty of the variation of the unmanned aerial vehicle performance variables; tau isij: a running period;
where the function η describing the performance decay variable is τijAnd also with the parameter βiIn a non-linear relationship.
Preferably, the failure probability prediction value is calculated according to the following formula:
in the formula, T: running period parameter vectors; τ: the τ th operating cycle; y: a regression feature vector; p: a probability distribution function of the health characteristic value at the tau-th operation period; y isτ: performance decline characteristic value at the Tth operation period; dth: a predefined soft threshold.
The invention also provides a cluster landing sequencing system for the unmanned aerial vehicle, which comprises: the device comprises a calculation module, a communication module and a selection module;
a calculation module: each unmanned aerial vehicle in the unmanned aerial vehicle cluster calculates the failure probability predicted value according to the respective operation state data;
a communication module: each unmanned aerial vehicle is used for communicating with other unmanned aerial vehicles to obtain failure probability predicted values of all the unmanned aerial vehicles;
a selection module: and determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability predicted value.
Compared with the prior art, the invention has the beneficial effects that:
according to the technical scheme provided by the invention, the failure probability prediction value of each unmanned aerial vehicle in the unmanned aerial vehicle cluster is calculated by adopting a reliability prediction method through the operation state data of each unmanned aerial vehicle in the unmanned aerial vehicle cluster, and the unmanned aerial vehicle cluster is sequenced through the difference of physical properties, so that the landing serial number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster is determined, the subjectivity of manually specifying or randomly selecting the landing serial number by a program is avoided, the unmanned aerial vehicle with high reliability finally lands, and the probability of crash risk in the landing process of a fault unmanned aerial vehicle is reduced;
according to the technical scheme provided by the invention, the predicted value of the failure probability is independently calculated by the unmanned aerial vehicle, the state data of the unmanned aerial vehicle can be customized according to different requirements, and the unmanned aerial vehicle is suitable for various unmanned aerial vehicle models, can be applied to unmanned aerial vehicle clustering and can also be applied to warehousing sequencing of intelligent group robots.
The technical scheme provided by the invention is easy to understand, simple to implement and wide in applicability.
Drawings
FIG. 1 is a schematic diagram of a coordinated landing sequencing method for unmanned aerial vehicle clusters according to the present invention;
FIG. 2 is a schematic diagram of an unmanned aerial vehicle cluster landing sequencing system of the present invention;
FIG. 3 is a frame diagram of the unmanned aerial vehicle cluster cooperative landing sequencing method of the present invention;
fig. 4 is a diagram of a relationship between the data processing unit of the unmanned aerial vehicle, the performance degradation track, and the health characteristic value in embodiment 3 of the present invention;
fig. 5 is a flowchart of a process of calculating a health characteristic value and a failure probability prediction value of an unmanned aerial vehicle in a future operating period in embodiment 3 of the present invention;
fig. 6 is a schematic diagram of a method for predicting health characteristics of an unmanned aerial vehicle in a future operating cycle in embodiment 3 of the present invention;
fig. 7 is a performance degradation trajectory of an unmanned aerial vehicle numbered UAV _ ID ═ 1 in embodiment 3 of the present invention;
fig. 8 is a predicted value of failure probability of the unmanned aerial vehicle in a future operating period in embodiment 3 of the present invention;
fig. 9 is a schematic view of communication between drones for broadcasting and subscribing to messages in embodiment 3 of the present invention.
Detailed Description
For a better understanding of the present invention, reference is made to the following description taken in conjunction with the accompanying drawings and examples.
Example 1:
an unmanned aerial vehicle cluster cooperative landing sequencing method is shown in fig. 1, and includes:
step 1: each unmanned aerial vehicle in the unmanned aerial vehicle cluster calculates the failure probability predicted value of the unmanned aerial vehicle according to the respective operation state data;
step 2: each unmanned aerial vehicle communicates with other unmanned aerial vehicles in the unmanned aerial vehicle cluster to obtain failure probability predicted values of all unmanned aerial vehicles;
and step 3: and determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability predicted value.
Step 1: each unmanned aerial vehicle in the unmanned aerial vehicle cluster calculates the failure probability predicted value thereof according to the respective operation state data, and the failure probability predicted value comprises the following steps:
each unmanned aerial vehicle calculates the health characteristic value thereof according to the respective running state data;
and calculating the failure probability predicted value of the health characteristic value according to the health characteristic value.
Specifically, the health characteristic value is an euclidean distance between current operating state data of the unmanned aerial vehicle and positive sample data, or an euclidean distance between an input vector and a best matching neural unit;
the input vector is a vector formed by a one-dimensional vector formed by rough features corresponding to the current operation state data of the unmanned aerial vehicle in a certain time period.
Specifically, the euclidean distance between the current operating state data and the positive sample data is calculated according to the following formula:
in the formula (d)ij: the Euclidean distance between the state data of the unmanned aerial vehicle with the number i in the jth operation period and the positive sample data; m: the number of the coarse characteristic values collected in the jth operation period; xik: the current state data is the state data of the unmanned aerial vehicle with the number i in the jth operation cycle; u. ofik: positive sample data; i: numbering unmanned aerial vehicles; j: the jth run cycle.
Preferably, the coarse signature refers to the preliminary signature data of all data parsed from the flight control panel. For example, a vector of means, variance, maximum, minimum, etc. And further transforming the coarse characteristic to obtain a fine characteristic, namely a health characteristic value.
The expression for similarity measurement of Euclidean distances by using Gaussian kernel function is as follows:
wherein s isj: at presentSimilarity between state data and positive sample data; h: the width of the kernel function.
The other calculation scheme is to calculate the health characteristic value of the unmanned aerial vehicle by adopting a self-organizing characteristic mapping model. The self-organizing feature mapping model is a neural network structure formed by an input layer and a competition layer, and each neuron between the two layers is connected in a two-way mode without an implied layer. For each vector U (t) input into the self-organizing feature mapping model, a group of distance sequences are obtained by calculating Euclidean distances between the weight vector of each neuron in the self-organizing feature mapping model and U (t), and the neuron corresponding to the minimum value in the distance sequences is called as a best matching neural unit (BMU). The positive sample data is mostly clustered within a certain distance range of the best matching neural unit. And updating the weight vector of the best matching neural unit and each neighbor neuron thereof according to the learning function so as to be excited and suppressed respectively until reaching a preset training frequency or the weight change amount in each learning is less than a certain threshold value.
And calculating a minimum quantization error vector based on the self-organizing feature mapping model, performing optimization weighted fusion on the minimum quantization error vector to obtain an optimal performance degradation track, and training parameters of the self-organizing feature mapping model by adopting positive sample data. The weight vectors of the best matching neural unit and the adjacent neurons thereof are adjusted relative to the input vector along with the time change, and the expression of the learning function is as follows:
Wi(t+1)＝Wi(t)-α(t)·hci(t)·(Ui(t)-Wi(t))
in the formula, t +1 and t respectively represent two adjacent moments; wi represents a weight vector of the ith neuron; h isci(t) is the manner in which neighboring neurons are acquired at time t.
The minimum quantization error is defined as the euclidean distance between the input vector u (t) and the best matching neural unit, i.e. the minimum quantization error is taken as a healthy characteristic value at a certain time.
The euclidean distance between the input vector u (t) and the best matching neural unit is calculated as follows:
in the formula: MQEt: the euclidean distance between the input vector u (t) and the BMU, i.e., the minimum quantization error; u (t): inputting a vector; BMU: a best matching neural unit of the self-organizing feature mapping model; f: a matrix Frobenius norm; t: the t-th time period;
the input vector U (t) is a coarse characteristic u corresponding to current operation state data output by a plurality of state sensors of the unmanned aerial vehicleijThe constructed one-dimensional vector is constructed as a vector in a time period t.
The performance degrading track is composed of the minimum quantization error of the operation periods 1 to t. For example, the performance degradation track of the drone numbered i is recorded as
Wherein, γi: the performance degradation track of the unmanned aerial vehicle with the number i;
the euclidean distance at the jth operating cycle for drone numbered i.
Specifically, the calculating of the failure probability prediction value of the health characteristic value according to the health characteristic value includes:
taking the health characteristic value as a decline characteristic value, and constructing a performance decline track model of the unmanned aerial vehicle by adopting a classical decline model;
sampling and calculating the performance degradation track model parameters by adopting a Monte Carlo method to obtain a possible degradation track;
and calculating a failure probability predicted value in a future operation period according to the possible decline orbit and a preset soft threshold value.
Specifically, the performance degradation trajectory model is shown as follows:
yij＝η(τij,φ,βi)+ξij
in the formula, yij: health characteristics of unmanned aerial vehicle with number i in j-th operation periodValue η function describing performance decay variables, phi constant, βiThe decline rate of the unmanned plane with number i ξij: error terms of uncertainty of the variation of the unmanned aerial vehicle performance variables; tau isij: a running period;
where the function η describing the performance decay variable is τijAnd also with the parameter βiIn a non-linear relationship.
Wherein η is τijAnd also with the parameter βiIn a non-linear relationship.
Assuming that a sequence of random error terms satisfies
The normal distribution of the number of the channels is normal,
the variance of the error.
Variance of error
Obeying the posterior distribution expression as:
in the formula, y: a regression feature vector; t: a service period parameter vector; n-k: inverse Chi2Degree of freedom of distribution, k is a constraint number, n: the number of regression feature vector samples;
assuming unknown parameters performance degradation rate βiSatisfying the prior distribution expression as:
in the formula (I), the compound is shown in the specification,
according to the current measured health characteristic value and the prior information obtained in advance, the method comprises the following steps: and estimating model parameters according to the initial degradation value, the mean value and the variance of the degradation rate.
Specifically, the failure probability prediction value is calculated according to the following formula:
in the formula, T: running period parameter vectors; τ: the τ th operating cycle; y: a regression feature vector; p: a probability distribution function of the health characteristic value at the tau-th operation period; y isτ: performance decline characteristic value at the Tth operation period; dth: a predefined soft threshold.
Step 2: each unmanned aerial vehicle communicates with other unmanned aerial vehicles in the unmanned aerial vehicle cluster to obtain failure probability predicted values of all unmanned aerial vehicles;
specifically, communicating each drone with other drones in the cluster of drones includes
Each unmanned aerial vehicle broadcasts a failure probability predicted value in the unmanned aerial vehicle cluster; and simultaneously subscribing the failure probability predicted values of other unmanned aerial vehicles.
Unmanned aerial vehicles in the unmanned aerial vehicle cluster communicate with each other, before executing tasks, the failure probability prediction value of each unmanned aerial vehicle is broadcasted, and meanwhile, the failure probabilities of other unmanned aerial vehicles are subscribed. In order to obtain the predicted failure probability values of all the drones for each drone, the time for broadcasting and subscribing the messages between the drones is as long as possible, considering the situation that the poor communication reliability can cause the messages sent by a part of drones not to be received. For example, for a cluster of 30 fixed wing drones, the duration of the broadcast and subscription messages is 2 minutes when there are unreliable contributors such as breaks in communication between drones.
and each unmanned aerial vehicle selects the unmanned aerial vehicle with the minimum failure probability predicted value from the acquired failure probability predicted values of all unmanned aerial vehicles including the unmanned aerial vehicle to land finally.
If the type of unmanned aerial vehicle is diversified in the cluster to various unmanned aerial vehicle quantity is different, only need select the strongest big unmanned aerial vehicle of function as the pilot, and other unmanned aerial vehicles are the follower. The follower adopts the landing sequencing method of the patent, and the pilot lands at last.
Example 2:
based on the same inventive concept, the present invention further provides an unmanned aerial vehicle cluster landing sequencing system, as shown in fig. 2, including: the device comprises a calculation module, a communication module and a selection module;
a calculation module: each unmanned aerial vehicle in the unmanned aerial vehicle cluster calculates the failure probability predicted value according to the respective operation state data;
a communication module: each unmanned aerial vehicle is used for communicating with other unmanned aerial vehicles to obtain failure probability predicted values of all the unmanned aerial vehicles;
a selection module: and determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability predicted value.
The calculation module comprises a first calculation submodule and a second calculation submodule; a first calculation submodule: the system is used for calculating the health characteristic value of each unmanned aerial vehicle according to the respective running state data; a second calculation submodule: and the failure probability prediction value of the user is calculated according to the health characteristic value.
In the first calculation submodule, the health characteristic value is the Euclidean distance between the current operation state data of the unmanned aerial vehicle and positive sample data, or the Euclidean distance between an input vector and the best matching neural unit;
the input vector is a vector formed by a one-dimensional vector formed by rough features corresponding to the current operation state data of the unmanned aerial vehicle in a certain time period.
Specifically, the euclidean distance between the current operating state data and the positive sample data is calculated according to the following formula:
in the formula (d)ij: the Euclidean distance between the state data of the unmanned aerial vehicle with the number i in the jth operation period and the positive sample data; m: the number of the coarse characteristic values collected in the jth operation period; xik: the current state data is the state data of the unmanned aerial vehicle with the number i in the jth operation cycle; u. ofik: positive sample data; i: numbering unmanned aerial vehicles; j: the jth run cycle.
The euclidean distance between the input vector u (t) and the best matching neural unit is calculated as follows:
in the formula: MQEt: the euclidean distance between the input vector u (t) and the BMU, i.e., the minimum quantization error; u (t): inputting a vector; BMU: a best matching neural unit of the self-organizing feature mapping model; f: a matrix Frobenius norm; t: the t-th time period;
the input vector U (t) is a coarse feature u corresponding to a plurality of state sensor output data of the unmanned aerial vehicleijThe constructed one-dimensional vector is constructed as a vector over successive time periods t.
In the second calculation sub-module, the calculating the failure probability prediction value of the second calculation sub-module according to the health characteristic value includes:
taking the health characteristic value as a decline characteristic value, and constructing a performance decline track model of the unmanned aerial vehicle by adopting a classical decline model;
sampling and calculating the performance degradation track model parameters by adopting a Monte Carlo method to obtain a possible degradation track;
and calculating a failure probability predicted value in a future operation period according to the possible decline orbit and a preset soft threshold value.
Preferably, the performance degradation trajectory model is as follows:
yij＝η(τij,φ,βi)+ξij
in the formula, yijHealth characteristic value of unmanned plane with number i in operation period j, η function describing performance degradation variable, phi constant, βiThe decline rate of the unmanned plane with number i ξij: error terms of uncertainty of the variation of the unmanned aerial vehicle performance variables; tau isij: a running period;
where the function η describing the performance decay variable is τijAnd also with the parameter βiIn a non-linear relationship.
Preferably, the failure probability prediction value is calculated according to the following formula:
in the formula, T: running period parameter vectors; τ: the τ th operating cycle; y: a regression feature vector; p: a probability distribution function of the health characteristic value at the tau-th operation period; y isτ: performance decline characteristic value at the Tth operation period; dth: a predefined soft threshold.
In the selection module, according to the failure probability predicted value, determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster comprises:
and each unmanned aerial vehicle selects the unmanned aerial vehicle with the minimum failure probability predicted value from the acquired failure probability predicted values of all unmanned aerial vehicles including the unmanned aerial vehicle to land finally.
Example 3:
in an application scene of the unmanned aerial vehicle cluster, the unmanned aerial vehicle cluster provided with the swarm intelligent operating system executes tasks in a certain area and is in an aggregation state before landing. The unmanned aerial vehicle cluster has 6 total quadrotor unmanned aerial vehicles, the number is recorded as UAV _ ID being 1, UAV _ ID being 2, UAV _ ID being 3, UAV _ ID being 4, UAV _ ID being 5 and UAV _ ID being 6.
An unmanned aerial vehicle cluster cooperative landing sequencing method is shown in fig. 3, the overall architecture is based on the idea of distributed edge calculation, an unmanned aerial vehicle in an unmanned aerial vehicle cluster calculates a failure probability predicted value of a certain future operating period, and broadcasts the failure probability predicted value to other unmanned aerial vehicles, and the specific steps are as follows:
step 1: each unmanned aerial vehicle in the unmanned aerial vehicle cluster calculates the failure probability predicted value of the unmanned aerial vehicle according to the respective operation state data;
analyzing flight state data from a flight controller interface of an unmanned aerial vehicle in the cluster to obtain performance degradation coarse characteristic values, and calculating to obtain respective health characteristic values;
communication protocol information that four rotor unmanned aerial vehicle flight control ware adopted is as follows:
the resolved flight status data is stored as a rossbag file, and the format of the stored message is as follows:
the Rosbag file stored by a Robot Operating System (ROS) is converted into a txt format, and the obtained column vectors are respectively as follows: time stamps, data frames, relative coordinates northeast (unit: m), airspeed (unit: m/s), airborne sensor data, and the like.
Calculating the health characteristic value of the unmanned aerial vehicle by adopting a self-organizing characteristic mapping model, and constructing a performance decline track model of the unmanned aerial vehicle; sampling and calculating the performance degradation track model parameters by adopting a Monte Carlo method to obtain a possible degradation track; and calculating a failure probability predicted value in a future operation period according to the possible decline orbit and a preset soft threshold value. A diagram of the relationship between the performance degradation trajectory and the health characteristic value is shown in fig. 4. Wherein, the performance degradation orbit gamma of the unmanned aerial vehicle with the number of iiIs determined by the health characteristic value MQE1:tAnd (4) forming.
The health characteristic value calculated based on the self-organizing kernel regression model or the neural network model is used as an input variable of the performance degradation prediction model, the performance degradation prediction model adopts a classical state space model, a simulated sampling algorithm, namely a Monte Carlo method, is used for simulating the performance degradation track of the unmanned aerial vehicle, the number of times of reaching a soft threshold value of the performance degradation track in a certain running period in the future and the simulation number of the degradation track are counted, the ratio is used as probability distribution estimation, then the failure probability prediction value is calculated, and the calculation process of the health characteristic value and the failure probability prediction of the unmanned aerial vehicle is shown in figure 5.
Fig. 6 is a schematic diagram of a health characteristic value prediction method for a future operating cycle of the unmanned aerial vehicle, wherein 101 is a predicted performance degradation trajectory; 102-historical operating cycle; 103-current running period; 104 — some operating period in the future.
Fig. 7 shows the performance degradation trajectory of the cluster numbered UAV _ ID 1 drone, where the performance degradation trajectory is a curve obtained by fitting an exponential function to the health feature value. The performance degrading track shapes of all drones in the cluster are similar.
After a performance degradation track y formed by health characteristic values is obtained, error variance in a performance degradation track model is calculated by adopting error variance posterior distribution
And obtaining a performance decline prediction model. And then sampling and calculating parameters of the performance degradation track model, counting the number of times of reaching a soft threshold value of the performance degradation track and the degradation track simulation number of times of reaching the soft threshold value in the future in a certain running period on the basis of simulating the performance degradation track path of the unmanned aerial vehicle by adopting a Monte Carlo method, taking the ratio of the number of times of reaching the soft threshold value of the performance degradation track and the degradation track simulation number of times as probability distribution estimation, and calculating the cumulative failure probability. The performance degradation orbit value of j different operation periods is solved as y1,…,yjThe corresponding operating period is recorded as tau1,…,τj. And calculating the performance decline track path of the unmanned aerial vehicle by adopting a Monte Carlo method to generate the number of the tracks of 50000. Fig. 8 shows the predicted failure probability values of drones in the cluster in a future operating period.
Step 2: each unmanned aerial vehicle communicates with other unmanned aerial vehicles in the unmanned aerial vehicle cluster to obtain failure probability predicted values of all unmanned aerial vehicles;
at a given time before the task is executed, the group intelligent operating system switches to a cluster co-landing sequencing plug-in. The drones with the numbers UAV _ ID ≠ i, i ═ 1, 2, …, 6, broadcast their respective failure probability predictors, while the subscription numbers UAV _ ID ≠ i drone failure probability predictors. The process of subscribing a single drone to the predicted failure probability values of all drones in the cluster is shown in fig. 9.
And step 3: and determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability predicted value.
The unmanned aerial vehicle has an independent calculation function, after subscribing failure probability predicted values of other unmanned aerial vehicles in the unmanned aerial vehicle cluster, the failure probability predicted values of all the unmanned aerial vehicles are ranked, and one unmanned aerial vehicle UAV _ ID with the minimum value is selected to be 4 for preferential landing.
The method does not limit the type and size of the unmanned aerial vehicle, the unmanned aerial vehicle can be a multi-rotor, a fixed wing and a mixer, and the sensor for collecting state data installed on the unmanned aerial vehicle is not limited to acceleration, temperature, humidity, height, a vision camera and the like, and can also be installed with other required sensors.
The method can be applied to a group intelligent operation system, and the application field is not limited to unmanned plane clusters, and can also be the sequencing problem of group intelligent robots.
The facts show that the technical scheme provided by the invention adopts a reliability prediction method, and the unmanned aerial vehicle clusters are sorted through the difference of physical properties, so that the subjectivity of manual designation or random selection of landing sequence numbers by a program is avoided;
according to the technical scheme provided by the invention, the failure probability predicted value is independently calculated by the unmanned aerial vehicle, and the state data of the unmanned aerial vehicle can be customized according to different requirements, so that the unmanned aerial vehicle cluster system is suitable for various unmanned aerial vehicle models, and can be applied to unmanned aerial vehicle clusters and intelligent group robots.
The technical scheme provided by the invention is easy to understand, simple to implement and wide in applicability.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the claims of the present invention which are filed as the application.
Claims (10)
1. An unmanned aerial vehicle cluster cooperative landing sequencing method is characterized by comprising the following steps:
each unmanned aerial vehicle in the unmanned aerial vehicle cluster calculates the failure probability predicted value of the unmanned aerial vehicle according to the respective operation state data;
each unmanned aerial vehicle communicates with other unmanned aerial vehicles in the unmanned aerial vehicle cluster to obtain failure probability predicted values of all unmanned aerial vehicles;
and determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability predicted value.
2. The coordinated landing sequencing method for unmanned aerial vehicle cluster as claimed in claim 1, wherein the step of calculating the failure probability prediction value of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the respective operation state data comprises:
each unmanned aerial vehicle calculates the health characteristic value thereof according to the respective running state data;
and calculating the failure probability predicted value of the health characteristic value according to the health characteristic value.
3. The method of sequencing for coordinated landing of a cluster of drones as recited in claim 1, wherein said each drone communicating with other drones in the cluster of drones comprises
Each unmanned aerial vehicle broadcasts a failure probability predicted value in the unmanned aerial vehicle cluster; and simultaneously subscribing the failure probability predicted values of other unmanned aerial vehicles.
4. The unmanned aerial vehicle cluster cooperative landing sequencing method of claim 1, wherein determining a landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability prediction value comprises:
and each unmanned aerial vehicle selects the unmanned aerial vehicle with the minimum failure probability predicted value from the acquired failure probability predicted values of all unmanned aerial vehicles including the unmanned aerial vehicle to land finally.
5. The method for sequencing coordinated landing of unmanned aerial vehicle cluster according to claim 2, wherein the health characteristic value is the euclidean distance between the current operating state data of the unmanned aerial vehicle and the positive sample data, or the euclidean distance between the input vector and the best matching neural unit;
the input vector is a vector formed by a one-dimensional vector formed by rough features corresponding to the current operation state data of the unmanned aerial vehicle in a certain operation period.
6. The unmanned aerial vehicle cluster cooperative landing ranking method of claim 5, wherein the Euclidean distance between the current operating state data and the positive sample data is calculated according to the following formula:
in the formula (d)ij: the Euclidean distance between the state data of the unmanned aerial vehicle with the number i in the jth operation period and the positive sample data; m: the number of the coarse characteristic values collected in the jth operation period; xik: the current state data is the state data of the unmanned aerial vehicle with the number i in the jth operation cycle; u. ofik: positive sample data; i: numbering unmanned aerial vehicles; j: the jth run cycle.
Preferably, the euclidean distance between the input vector u (t) and the best matching neural unit is calculated as follows:
in the formula: MQEt: the euclidean distance between the input vector u (t) and the BMU, i.e., the minimum quantization error; u (t): inputting a vector; BMU: self-organizing feature mapping modelA best-matching neural unit of type; f: a matrix Frobenius norm; t: the t-th operation cycle.
7. The method of claim 2, wherein the calculating the failure probability prediction value of the drone cluster based on the health eigenvalue comprises:
taking the health characteristic value as a decline characteristic value, and constructing a performance decline track model of the unmanned aerial vehicle by adopting a classical decline model;
sampling and calculating the performance degradation track model parameters by adopting a Monte Carlo method to obtain possible degradation tracks;
and calculating a failure probability predicted value in a future operation period according to the possible decline orbit and a preset soft threshold value.
8. The unmanned aerial vehicle cluster cooperative landing sequencing method of claim 7, wherein the performance decay trajectory model is as follows:
yij＝η(τij,φ,βi)+ξij
in the formula, yijHealth characteristic value of unmanned plane with number i in operation period j, η function describing performance degradation variable, phi constant, βiThe decline rate of the unmanned plane with number i ξij: error terms of uncertainty of the variation of the unmanned aerial vehicle performance variables; tau isij: a running period;
where the function η describing the performance decay variable is τijAnd also with the parameter βiIn a non-linear relationship.
9. The unmanned aerial vehicle cluster cooperative landing ranking method of claim 7, wherein the failure probability prediction value is calculated according to the following equation:
in the formula, T: running period parameter vectors; τ: the τ th operating cycle; y: a regression feature vector; p: a probability distribution function of the health characteristic value at the tau-th operation period; y isτ: performance decline characteristic value at the Tth operation period; dth: a predefined soft threshold.
10. An unmanned aerial vehicle cluster landing sequencing system, the system comprising: the device comprises a calculation module, a communication module and a selection module;
a calculation module: each unmanned aerial vehicle in the unmanned aerial vehicle cluster calculates the failure probability predicted value according to the respective operation state data;
a communication module: each unmanned aerial vehicle is used for communicating with other unmanned aerial vehicles to obtain failure probability predicted values of all the unmanned aerial vehicles;
a selection module: and determining the landing sequence number of each unmanned aerial vehicle in the unmanned aerial vehicle cluster according to the failure probability predicted value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010101115.5A CN111368971B (en) | 2020-02-19 | 2020-02-19 | Unmanned aerial vehicle cluster cooperative landing sequencing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010101115.5A CN111368971B (en) | 2020-02-19 | 2020-02-19 | Unmanned aerial vehicle cluster cooperative landing sequencing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111368971A true CN111368971A (en) | 2020-07-03 |
| CN111368971B CN111368971B (en) | 2021-01-08 |
Family
ID=71210979
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010101115.5A Expired - Fee Related CN111368971B (en) | 2020-02-19 | 2020-02-19 | Unmanned aerial vehicle cluster cooperative landing sequencing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111368971B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743461A (en) * | 2021-07-29 | 2021-12-03 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle cluster health degree assessment method and device |
| CN113852994A (en) * | 2021-11-18 | 2021-12-28 | 南京信息工程大学 | High-altitude base station cluster auxiliary edge calculation method used in emergency communication |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107179777A (en) * | 2017-06-03 | 2017-09-19 | 复旦大学 | Multiple agent cluster Synergistic method and multiple no-manned plane cluster cooperative system |
| CN107357313A (en) * | 2017-08-15 | 2017-11-17 | 成都优艾维智能科技有限责任公司 | Power transmission line fault maintenance system and method based on unmanned aerial vehicle inspection image |
| CN107807670A (en) * | 2017-12-21 | 2018-03-16 | 合肥灵猫传媒有限公司 | A kind of unmanned plane cluster flight control system |
| CN107861519A (en) * | 2017-11-06 | 2018-03-30 | 四川联众防务科技有限责任公司 | A kind of unmanned plane landing control system |
| CN107943086A (en) * | 2017-12-21 | 2018-04-20 | 合肥灵猫传媒有限公司 | A kind of unmanned plane cluster makes a return voyage control system |
| CN108196582A (en) * | 2018-02-12 | 2018-06-22 | 深圳技术大学（筹） | A kind of indoor Visual Navigation unmanned plane cluster flight control system and method |
| CN108388270A (en) * | 2018-03-21 | 2018-08-10 | 天津大学 | Cluster unmanned plane track posture cooperative control method towards security domain |
| CN108447309A (en) * | 2018-03-14 | 2018-08-24 | 广州亿航智能技术有限公司 | Unmanned plane landing method, apparatus and computer storage media |
| US20180307231A1 (en) * | 2017-04-19 | 2018-10-25 | 4D Tech Solutions, Inc. | Intelligent electronic speed controller (iesc) |
| CN108928744A (en) * | 2018-08-02 | 2018-12-04 | 深圳汇通智能化科技有限公司 | A kind of container crane inline diagnosis and maintenance system based on big data |
| CN109165472A (en) * | 2018-10-11 | 2019-01-08 | 北京航空航天大学 | A kind of power supply health evaluating method based on variable topological self-organizing network |
| CN109299210A (en) * | 2018-11-06 | 2019-02-01 | 哈尔滨工业大学（深圳） | A kind of multiple no-manned plane distributed collaboration searching method based on information fusion |
| CN109460065A (en) * | 2019-01-12 | 2019-03-12 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle cluster formation characteristic identification method and system based on potential function |
| CN109782797A (en) * | 2019-01-03 | 2019-05-21 | 中国科学院自动化研究所 | Multiple no-manned plane Synergistic method, system, device for multiple spot water quality sampling |
| CN110146108A (en) * | 2019-05-10 | 2019-08-20 | 南京航空航天大学 | A kind of On-line Fault appraisal procedure for unmanned plane bee colony collaborative navigation |
| CN110209195A (en) * | 2019-06-13 | 2019-09-06 | 浙江海洋大学 | The tele-control system and control method of marine unmanned plane |
-
2020
- 2020-02-19 CN CN202010101115.5A patent/CN111368971B/en not_active Expired - Fee Related
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180307231A1 (en) * | 2017-04-19 | 2018-10-25 | 4D Tech Solutions, Inc. | Intelligent electronic speed controller (iesc) |
| CN107179777A (en) * | 2017-06-03 | 2017-09-19 | 复旦大学 | Multiple agent cluster Synergistic method and multiple no-manned plane cluster cooperative system |
| CN107357313A (en) * | 2017-08-15 | 2017-11-17 | 成都优艾维智能科技有限责任公司 | Power transmission line fault maintenance system and method based on unmanned aerial vehicle inspection image |
| CN107861519A (en) * | 2017-11-06 | 2018-03-30 | 四川联众防务科技有限责任公司 | A kind of unmanned plane landing control system |
| CN107943086A (en) * | 2017-12-21 | 2018-04-20 | 合肥灵猫传媒有限公司 | A kind of unmanned plane cluster makes a return voyage control system |
| CN107807670A (en) * | 2017-12-21 | 2018-03-16 | 合肥灵猫传媒有限公司 | A kind of unmanned plane cluster flight control system |
| CN108196582A (en) * | 2018-02-12 | 2018-06-22 | 深圳技术大学（筹） | A kind of indoor Visual Navigation unmanned plane cluster flight control system and method |
| CN108447309A (en) * | 2018-03-14 | 2018-08-24 | 广州亿航智能技术有限公司 | Unmanned plane landing method, apparatus and computer storage media |
| CN108388270A (en) * | 2018-03-21 | 2018-08-10 | 天津大学 | Cluster unmanned plane track posture cooperative control method towards security domain |
| CN108928744A (en) * | 2018-08-02 | 2018-12-04 | 深圳汇通智能化科技有限公司 | A kind of container crane inline diagnosis and maintenance system based on big data |
| CN109165472A (en) * | 2018-10-11 | 2019-01-08 | 北京航空航天大学 | A kind of power supply health evaluating method based on variable topological self-organizing network |
| CN109299210A (en) * | 2018-11-06 | 2019-02-01 | 哈尔滨工业大学（深圳） | A kind of multiple no-manned plane distributed collaboration searching method based on information fusion |
| CN109782797A (en) * | 2019-01-03 | 2019-05-21 | 中国科学院自动化研究所 | Multiple no-manned plane Synergistic method, system, device for multiple spot water quality sampling |
| CN109460065A (en) * | 2019-01-12 | 2019-03-12 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle cluster formation characteristic identification method and system based on potential function |
| CN110146108A (en) * | 2019-05-10 | 2019-08-20 | 南京航空航天大学 | A kind of On-line Fault appraisal procedure for unmanned plane bee colony collaborative navigation |
| CN110209195A (en) * | 2019-06-13 | 2019-09-06 | 浙江海洋大学 | The tele-control system and control method of marine unmanned plane |
Non-Patent Citations (3)
| Title |
|---|
| 刘肩山: "无人机协同维修技术研究", 《航空装备维修技术及应用研讨会》 * |
| 杨瑶瑶: "无人机集群系统任务可靠性建模与评估技术", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 赵林 等: "基于突变理论设冷水泵转轴功能安全完整性评估", 《仪器仪表学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743461A (en) * | 2021-07-29 | 2021-12-03 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle cluster health degree assessment method and device |
| CN113743461B (en) * | 2021-07-29 | 2024-04-09 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle cluster health degree assessment method and device |
| CN113852994A (en) * | 2021-11-18 | 2021-12-28 | 南京信息工程大学 | High-altitude base station cluster auxiliary edge calculation method used in emergency communication |
| CN113852994B (en) * | 2021-11-18 | 2023-04-18 | 南京信息工程大学 | High-altitude base station cluster auxiliary edge calculation method used in emergency communication |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111368971B (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113313947B (en) | Road condition evaluation method of short-term traffic prediction graph convolution network | |
| CN109034376B (en) | L STM-based unmanned aerial vehicle flight state prediction method and system | |
| Baumann et al. | Deep reinforcement learning for event-triggered control | |
| CN111487991B (en) | Unmanned aerial vehicle cluster-oriented security level prediction method and system | |
| CN107886201B (en) | Multi-objective optimization method and device for multi-unmanned aerial vehicle task allocation | |
| CN111368971B (en) | Unmanned aerial vehicle cluster cooperative landing sequencing method and system | |
| CN109191922A (en) | A kind of extensive four-dimensional dynamic track prediction method and device | |
| CN112788699B (en) | Method and system for determining network topology of self-organizing network | |
| CN112257614A (en) | Station building passenger flow space-time distribution prediction method based on graph convolution network | |
| CN113359860B (en) | Unmanned aerial vehicle cluster reconstruction method based on communication state | |
| CN112417973A (en) | Unmanned system based on car networking | |
| Ong et al. | Short-term conflict resolution for unmanned aircraft traffic management | |
| CN111897224A (en) | Multi-agent formation control method based on actor-critic reinforcement learning and fuzzy logic | |
| Ghambari et al. | An enhanced NSGA-II for multiobjective UAV path planning in urban environments | |
| CN115223402B (en) | Airspace sector complexity prediction method based on space-time diagram convolutional network | |
| Sguerra et al. | Image classification using sum-product networks for autonomous flight of micro aerial vehicles | |
| CN112200391A (en) | Power distribution network edge side load prediction method based on k-nearest neighbor mutual information characteristic simplification | |
| CN112272074A (en) | Information transmission rate control method and system based on neural network | |
| Reily et al. | Adaptation to team composition changes for heterogeneous multi-robot sensor coverage | |
| Rodriguez-Fernandez et al. | Modelling behaviour in UAV operations using higher order double chain Markov models | |
| CN113516163B (en) | Vehicle classification model compression method, device and storage medium based on network pruning | |
| CN117875646A (en) | Multi-node multi-target task planning auxiliary generation method | |
| Kumar et al. | Graph learning based decision support for multi-aircraft take-off and landing at urban air mobility vertiports | |
| CN115514787B (en) | Intelligent unmanned aerial vehicle auxiliary decision-making planning method and device for Internet of vehicles environment | |
| CN111341102A (en) | Motion primitive library construction method and device and motion primitive connection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210108 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |